Alternatives
Products that do what OpenClaw Carapace – Security Scanner for OpenClaw does
Here's Openclaw Carapace, a CLI security scanner for OpenClaw. It audits your configs, flags CVEs, and scans skill files for vulnerabilities. A few things it does: - Auto-fix common misconfigurations - Hardening profiles for typical deployment patterns - SARIF output so it drops right into GitHub Code Scanning or your CI/CD pipeline Would love feedback — especially on what checks or hardening rules you'd want to see next.
- 1
- 2

- 3

- 4

- 5

- 6

- 7
- 8OO
2021 · github.com
- 9

- 10

- 11

- 12

- 13

- 14

- 15

- 16

File-based memory for OpenClaw with >92% retrieval accuracy
Mar 2026
- 17

13,000+ MCP servers, skills & plugins for AI coding agents
Jul 2026 · codexmarketplaces.com
- 18

- 19

- 20

- 21
- 22OD
Hello HN! I built OpenCodeSpace https://github.com/ngramai/opencodespace — a CLI tool that lets you launch disposable, self-hosted VS Code environments in one command. It’s like a self-hosted Code Spaces, but: - Works locally with Docker or remotely on Fly.io (AWS, GCE coming soon) - Auto-configured with Claude Code, OpenAI, Gemini CLI - Designed for YOLO mode development: temporary, parallel, throwaway sessions As Claude Code and Gemini CLI became core to my dev workflow, I kept needing a way to run them in parallel, in clean, isolated environments in full YOLO mode…
2025
- 23

- 24OS
I built a skill library for OpenClaw (always-on AI agent runtime, not session-based) where the agent can teach itself new behaviors during normal conversation. The idea: you tell your agent "every time I ask for a code review, always check for security issues first." It invokes a create-skill skill, writes a new SKILL.md, and that behavior is live immediately — no restart, no config change, no developer required. What I think is actually useful (the safety cluster): • loop-circuit-breaker: OpenClaw retries ALL errors identically. This halts on the 2nd identical failure before it burns your…
Mar 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →